└── README.md /README.md: -------------------------------------------------------------------------------- 1 | 2 | # Must-cared Multi-label Papers # 3 | 4 | This is a list of some important multi-label learning that serious students and researches working in the field should probably know about and read. 5 | 6 | This list is far from complete or objective, and is evolving, as important papers are being published year after year. Please let me know via [pull requests](https://github.com/XSilverBullet/Multi-label-Paper/pulls "pull requests") and [issues](https://github.com/XSilverBullet/Multi-label-Paper/issues "issues") if anything is missing. 7 | 8 | Also, I did not try to include links to original papers since there is a lot of work to keep dead links up to date. I'm sure most of the papers listed here via a single Google search by their titles. 9 | 10 | A paper does not have to be a peer-reviewed conference/journal paper to appear here. We also include tutial/survey-style papers and blog posts that often eaiser to understand than the original papers. 11 | 12 | ## Preliminary ## 13 | 14 | Minling Zhang: [A Review on Multi-Label Learning Algorithms](https://ieeexplore.ieee.org/document/#), in KDD 2013. 15 | 16 | Minling Zhang: [ML-KNN: A Lazy Learning Approach to Multi-Label Learning](http://xueshu.baidu.com/s?wd=paperuri%3A%28839c996d643b502366a3e172b4e205c3%29&filter=sc_long_sign&tn=SE_xueshusource_2kduw22v&sc_vurl=http%3A%2F%2Fwww.sciencedirect.com%2Fscience%2Farticle%2Fpii%2FS0031320307000027&ie=utf-8&sc_us=13138069364991137487), in Pattern Recognition 2007. 17 | 18 | Johannes Fürnkranz: [Multilabel Classification via Calibrated Label Ranking](http://link.springer.com/article/10.1007/s10994-008-5064-8), in Machine Learning 2008. 19 | 20 | Zhihua Zhou: [Multi-instance Multi-label Learning](http://xueshu.baidu.com/s?wd=paperuri%3A%2868eebebc5538e497fa42bca0816b67eb%29&filter=sc_long_sign&tn=SE_xueshusource_2kduw22v&sc_vurl=http%3A%2F%2Fdl.acm.org%2Fcitation.cfm%3Fid%3D2069972&ie=utf-8&sc_us=7632619167345951016), in Artificial Intelligence 2008. 21 | 22 | 23 | ## Long Tail ## 24 | Yuxiong Wang: [Learning to Model the Tail](https://papers.nips.cc/paper/7278-learning-to-model-the-tail), in NIPS 2017. 25 | 26 | Rohit Babbar: [Adversarial Extreme Multi-label Classification](https://arxiv.org/pdf/1803.01570.pdf), in arXiv 2018. 27 | 28 | ## Deep Learning ## 29 | Xuan Wu: [Multi-View Multi-Label Learning with View-Specific Information Extraction](), in IJCAI 19. 30 | 31 | Fernando Benites: [HARAM: A Hierarchical ARAM Neural Network for Large-scale Text Classification](http://doi.ieeecomputersociety.org/10.1109/ICDMW.2015.14), IEEE International Conference on Data Mining Workshops 2015. 32 | 33 | Jianqing Zhu: [Multi-label Convolutional Neural Network based Pedestrian Attribute Classification](http://xueshu.baidu.com/s?wd=paperuri%3A%28e1d5498801f8b037516b554573b4f8df%29&filter=sc_long_sign&tn=SE_xueshusource_2kduw22v&sc_vurl=http%3A%2F%2Fdl.acm.org%2Fcitation.cfm%3Fid%3D3063831&ie=utf-8&sc_us=117785351172552305), In Image & Vision Computing 2017. 34 | 35 | Wenjie Zhang: [Deep Extreme Multi-label Learning](https://arxiv.org/abs/1704.03718), arXiv preprint arXiv:1704.03718. 2017 Apr 12. 36 | 37 | CK Yeh: [Learning Deep Latent Spaces for Multi-Label Classification](http://www.aaai.org/ocs/index.php/AAAI/AAAI17/paper/download/14166/14487), in AAAI 2017. 38 | 39 | Sameera Ramasinghe: [A Context-aware Capsule Network for Multi-label Classification](https://arxiv.org/pdf/1810.06231), in arXiv 2018. 40 | 41 | Rami Aly: [Hierarchical Multi-label Classification of Text with Capsule Networks](), in ACL 2019. 42 | 43 | Pengcheng Yang: [SGM: Sequence Generation Model for Multi-Label Classification](https://www.baidu.com/link?url=BLefAuc6hWJ8uPfTjcjzd1BaTKfs1wVIn-VWxILNL2zH_DGDcLCZchgLedw5g0Hy&wd=&eqid=af29ebe70000d849000000055bd51d21), in COLING 2018. 44 | 45 | Pengcheng Yang: [A Deep Reinforced Sequence-to-Set Model for Multi-Label Text Classification](http://cn.arxiv.org/abs/1809.03118), in ACL 2019. 46 | 47 | Siddhartha Banerjee: [Hierarchical Transfer Learning for Multi-label Text Classification](), in ACL 2019. 48 | 49 | Yongcheng Liu: [Multi-Label Image Classification via Knowledge Distillation from Weakly-Supervised Detection](), in ACM Multimedia(MM) 2018. 50 | 51 | Shiyi He: [Reinforced Multi-Label Image Classification by Exploring Curriculum](), in AAAI 2018. 52 | 53 | Jiang Wang: [CNN-RNN: A Unified Framework for Multi-label Image Classification](https://arxiv.org/abs/1604.04573), in CVPR 2016. 54 | 55 | Yunchao Wei: [HCP: A Flexible CNN Framework for Multi-Label Image Classification](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7305792&tag=1), in TPAMI 2016. 56 | 57 | Tianshui Chen: [Recurrent Attentional Reinforcement Learning for Multi-label Image Recognition](https://arxiv.org/pdf/1712.07465.pdf), in AAAI 2018. 58 | 59 | Thibaut Durand: [Learning a Deep ConvNet for Multi-label Classification with Partial Labels](https://arxiv.org/pdf/1902.09720), in CVPR 2019. 60 | 61 | Zhaomin chen: [Multi-Label Image Recognition with Graph Convolutional Networks](https://arxiv.org/pdf/1904.03582), in CVPR 2019. 62 | 63 | ## Hierarchical Multi-Label ## 64 | JônatasWehrmann: [Hierarchical Multi-Label Classification Networks](http://proceedings.mlr.press/v80/wehrmann18a.html), in ICML 2018. 65 | 66 | ## Label Tree or Graph Learning ## 67 | Samy Bengio: [ Label Embedding Trees for Large Multi-Class Tasks](https://papers.nips.cc/paper/4027-label-embedding-trees-for-large-multi-class-tasks), in NIPS 2010. 68 | 69 | Jia Deng: [Fast and Balanced: Efficient Label Tree Learning for Large Scale Object Recognition](http://vision.stanford.edu/pdf/NIPS2011_0391.pdf), in NIPS 2011. 70 | 71 | Wei Bi: [Multi-Label Classification on Tree-and DAG Structured](http://xueshu.baidu.com/s?wd=paperuri%3A%287cf023b6fd8a4cf2eb5478dc8a0ff2dc%29&filter=sc_long_sign&tn=SE_xueshusource_2kduw22v&sc_vurl=http%3A%2F%2Fdl.acm.org%2Fcitation.cfm%3Fid%3D3104485&ie=utf-8&sc_us=11672686252934049672), in ICML 2011. 72 | 73 | Piotr Szyma´nski: [LNEMLC: Label Network Embeddings for Multi-Label Classifiation](https://arxiv.org/abs/1812.02956), in Arxiv 2018. 74 | 75 | ## Embedding ## 76 | Xin Li: [Multi-Label Classification with Feature-Aware Non-Linear Label Space Transformation](http://www.ijcai.org/Proceedings/15/Papers/511.pdf), in IJCAI 2015. 77 | 78 | Keigo Kimura: [Simultaneous Nonlinear Label-Instance Embedding for Multi-label Classification](http://www.springer.com/cda/content/document/cda_downloaddocument/9783319490540-c2.pdf?SGWID=0-0-45-1594207-p180397937), in Joint IAPR 2016. 79 | 80 | ## Self-spaced Multi-Label Learning ## 81 | Cheng Gong: [Teaching-to-Learning-to-Teach for Multi-Label Propagation](http://www.ee.columbia.edu/~wliu/AAAI16_MultiLP.pdf), in AAAI 2016. 82 | 83 | ## Matrix Completion ## 84 | Kang Zhao: [Top-N Recommender System via Matrix Completion](http://www.aaai.org/ocs/index.php/AAAI/AAAI16/paper/download/11824/11581), in AAAI 2016 85 | 86 | Joonseok Lee: [Local Collaborative Ranking](https://dl.acm.org/citation.cfm?id=2567970), in WWW pp 85-96 ACM 2014. 87 | 88 | ## Online Learning ## 89 | Steven C. H. Hoi: [Online Learning: A Comprehensive Survey](http://cn.arxiv.org/abs/1802.02871v2), in CoRR 2018. 90 | 91 | Young hun Jung: [Online Boosting Algorithms for Multi-label Ranking](http://cn.arxiv.org/abs/1710.08079), in arXiv 2017. 92 | 93 | Hongming Chu: [Dynamic Principal Projection for Cost-Sensitive Online Multi-Label Classification](http://cn.arxiv.org/abs/1711.05060), in CoRR 2017. 94 | 95 | Alican Büyükçakır: [A Novel Online Stacked Ensemble for Multi-Label Stream Classification](http://cn.arxiv.org/abs/1809.09994), in ACM CIKM 2018. 96 | 97 | Sophie Burkhardt1: [Online multi-label dependency topic models for text classification](https://link.springer.com/article/10.1007/s10994-017-5689-6), in Machine Learning vol 107 pp 859-886 2018. 98 | 99 | Zahra Ahmadi: [Online Multi-Label Classification: A Label Compression Method](http://cn.arxiv.org/abs/1804.01491), in Pattern Recognition Letters(PRL) 2018. 100 | 101 | Aljaž Osojnik: [Multi-label Classification via Multi-target Regression on Data Streams](https://link.springer.com/article/10.1007%2Fs10994-016-5613-5), in Machine Learning vol 2016 pp 745-770 2017. 102 | 103 | ## Others ## 104 | Shan You: [Privileged Multi-Label Learning](https://www.ijcai.org/proceedings/2017/0466.pdf), in IJCAI 2017. 105 | 106 | Shenjun Huang: [Multi-Label Hypothesis Reuse](http://xueshu.baidu.com/s?wd=paperuri%3A%28981a1ee84cce9088e3599d463a07784f%29&filter=sc_long_sign&tn=SE_xueshusource_2kduw22v&sc_vurl=http%3A%2F%2Fdl.acm.org%2Fcitation.cfm%3Fid%3D2339615&ie=utf-8&sc_us=12857114202461647535), in KDD (Best Paper) 2012. 107 | 108 | Mingkun Xie: [Partial Multi-Label Learning](), in AAAI 2018. 109 | 110 | Qianwen Zhang: [Feature-Induced Labeling Information Enrichment for Multi-Label Learning](), in AAAI 2018. 111 | 112 | Lei Feng: [Collaboration based Multi-Label Learning](), in AAAI 2019. 113 | 114 | Wu Jiawei: [Learning to Learn and Predict: A Meta-Learning Approach for Multi-Label Classification](https://arxiv.org/pdf/1909.04176.pdf), in EMNLP 2019. --------------------------------------------------------------------------------